ai-ml

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's RAG and document-processing workflows (see references/rag-patterns.md and the SKILL.md sections on "Document Processing" and "RAG Architecture") explicitly describe fetching and ingesting HTML/PDF/online documents (via tools like trafilatura/BeautifulSoup and web/document loaders) and passing retrieved third‑party content into prompts/context for generation, so untrusted public web or user-created content can be read and materially influence agent actions.